I am working on text normalization. I have descriptions of variables/attributes, which I need to convert to correct english.
A an example is shown below:
"This is the sta of the customer's order"
The word 'sta' above needs to be converted to 'status' based on the error and the context.
I tried out a character level encoder decoder architecture, but did not get good results.I need some direction on how to approach this problem.
input :"This is the sta of the customer's order"
output: "This is the status of the customer's order"
This is called spell checking. There are ways to do so, one common way is to use minimum edit distance. An edit is one of these actions : adding a char, removing a char, replacing a char with another, transposing two adjacent chars. You can use edits to make new words out of mistaken words, and use a dictionary to see if the word really exists in English language. There may be more than 1 candidate for each incorrect word to choose from. There are also ways for candidate ranking.
Reading this paper may be a good start :
A Survey of Spelling Error Detection and Correction Techniques
Related
My team is using Solr and I have a question regarding it.
There are some search terms which doesn't gives relevant results or results which should have been displayed. For example:
Searching for Macy's without the apostrophe like "Macys" doesnt give back any result for Macy's.
Searching for JPMorgan vs JP Morgan gives different result
Searching for IBM doesn't show results which contains its full name i.e International business machine.
How can we improve and optimize such cases so that it gets applied to all, even to the one we didn't catch apart from these 3 above?
Any suggestions?
All these issues are related to how you process the incoming text for those fields. You'll have to create a filter chain for the field - and possibly use multiple fields for different use cases and prioritize those using qf - that processes the input values to do what you want.
Your first case can be solved by using a PatternReplaceFilter to remove any apostrophes - depending on your use case and tokenizer you might want to use the CharFilter version, as it processes the text before it's split into multiple tokens.
Your second case is a straight forward synonym filter or a WordDelimiterFilter, where you expand JPMorgan to "JP Morgan", or use the WordDelimiterFilter to expand case changes into separate tokens. That'll also allow you to search for JP and get JPMorgan related entries. These might have different effects on score, use debugQuery=true to see exactly how each term in your query contributes to the score.
The third case is in general the same as the second case. You'll have to create a decent synonym word list for the terms used, and this is usually something you build as you get feedback from your users, from existing dictionaries and from domain knowledge. There's also the option of preprocessing text using NLP, or in this case, something as primitive as indexing the initials of any capitalized words after each other could help.
I am looking for some general guidance here.
The high-level use case is such that I receive some product documents
from which I need to extract some information and process it. Before
doing that, I need to verify that the document is actually referring
to the correct product. For that I need to validate the product
heading/description from document against what I know to be correct.
So I have 2 texts
Text 1 - this refers to the product information extracted from some document
Text 2 - this is the actual product heading/description available with me, which can be considered as correct.
I need to validate that both texts refer to same product or object.
Example:
Text 1 (to be validated) - Optimus Prime Costume, Blue, with good packaging and warranty
Text 2 (correct info) - Optimus Prime Blue Costume, Medium Size`
You see, I need to validate that both text refer to Optimus Prime Costume.
I tried following methods -
Cosine Similarity
TF-IDF similarity
Overlapping words between strings
But the problem with them is that they depends on the entire text rather than the primary object being referred in the text.
I was thinking of processing as follows:-
Remove colors, size info etc. from the text 2. The text 2, is very concise and does not contain random data. It contains product name and size, colour info.
Validate that the remaining elements from Text 2 are present in Text 1, or atleast a majority of them are.
I am not quite sure what different NLP techniques might be there, which would be better than this approach, so any suggestions would be appreciated.
Depending on your target this can be medium-hard or very hard.
There are a couple of things you can use:
NER would definitely be helpful:
Wikifier could be useful too: http://cogcomp.org/page/demo_view/Wikifier
And also Semantic-Role-Labeling. See more annotations here: http://nlp.cogcomp.org/
It's hard to judge from one single example what is the exact algorithm, but if you have more examples might be easier to come up with a better formalization.
An extension of this can be found in what has been used
in this work.
I am a graduate student focusing on ML and NLP. I have a lot of data (8 million lines) and the text is usually badly written and contains so many spelling mistakes.
So i must go through some text cleaning and vectorizing. To do so, i considered two approaches:
First one:
cleaning text by replacing bad words using hunspell package which is a spell checker and morphological analyzer
+
tokenization
+
convert sentences to vectors using tf-idf
The problem here is that sometimes, Hunspell fails to provide the correct word and changes the misspelled word with another word that don't have the same meaning. Furthermore, hunspell does not reconize acronyms or abbreviation (which are very important in my case) and tends to replace them.
Second approache:
tokenization
+
using some embeddings methode (like word2vec) to convert words into vectors without cleaning text
I need to know if there is some (theoretical or empirical) way to compare this two approaches :)
Please do not hesitate to respond If you have any ideas to share, I'd love to discuss them with you.
Thank you in advance
I post this here just to summarise the comments in a longer form and give you a bit more commentary. No sure it will answer your question. If anything, it should show you why you should reconsider it.
Points about your question
Before I talk about your question, let me point a few things about your approaches. Word embeddings are essentially mathematical representations of meaning based on word distribution. They are the epitome of the phrase "You shall know a word by the company it keeps". In this sense, you will need very regular misspellings in order to get something useful out of a vector space approach. Something that could work out, for example, is US vs. UK spelling or shorthands like w8 vs. full forms like wait.
Another point I want to make clear (or perhaps you should do that) is that you are not looking to build a machine learning model here. You could consider the word embeddings that you could generate, a sort of a machine learning model but it's not. It's just a way of representing words with numbers.
You already have the answer to your question
You yourself have pointed out that using hunspell introduces new mistakes. It will be no doubt also the case with your other approach. If this is just a preprocessing step, I suggest you leave it at that. It is not something you need to prove. If for some reason you do want to dig into the problem, you could evaluate the effects of your methods through an external task as #lenz suggested.
How does external evaluation work?
When a task is too difficult to evaluate directly we use another task which is dependent on its output to draw conclusions about its success. In your case, it seems that you should pick a task that depends on individual words like document classification. Let's say that you have some sort of labels associated with your documents, say topics or types of news. Predicting these labels could be a legitimate way of evaluating the efficiency of your approaches. It is also a chance for you to see if they do more harm than good by comparing to the baseline of "dirty" data. Remember that it's about relative differences and the actual performance of the task is of no importance.
I'm embarking on a project for a non-profit organization to help process and classify 1000's of reports annually from their field workers / contractors the world over. I'm relatively new to NLP and as such wanted to seek the group's guidance on the approach to solve our problem.
I'll highlight the current process, and our challenges and would love your help on the best way to solve our problem.
Current process: Field officers submit reports from locally run projects in the form of best practices. These reports are then processed by a full-time team of curators who (i) ensure they adhere to a best-practice template and (ii) edit the documents to improve language/style/grammar.
Challenge: As the number of field workers increased the volume of reports being generated has grown and our editors are now becoming the bottle-neck.
Solution: We would like to automate the 1st step of our process i.e., checking the document for compliance to the organizational best practice template
Basically, we need to ensure every report has 3 components namely:
1. States its purpose: What topic / problem does this best practice address?
2. Identifies Audience: Who is this for?
3. Highlights Relevance: What can the reader do after reading it?
Here's an example of a good report submission.
"This document introduces techniques for successfully applying best practices across developing countries. This study is intended to help low-income farmers identify a set of best practices for pricing agricultural products in places where there is no price transparency. By implementing these processes, farmers will be able to get better prices for their produce and raise their household incomes."
As of now, our approach has been to use RegEx and check for keywords. i.e., to check for compliance we use the following logic:
1 To check "states purpose" = we do a regex to match 'purpose', 'intent'
2 To check "identifies audience" = we do a regex to match with 'identifies', 'is for'
3 To check "highlights relevance" = we do a regex to match with 'able to', 'allows', 'enables'
The current approach of RegEx seems very primitive and limited so I wanted to ask the community if there is a better way to solving this problem using something like NLTK, CoreNLP.
Thanks in advance.
Interesting problem, i believe its a thorough research problem! In natural language processing, there are few techniques that learn and extract template from text and then can use them as gold annotation to identify whether a document follows the template structure. Researchers used this kind of system for automatic question answering (extract templates from question and then answer them). But in your case its more difficult as you need to learn the structure from a report. In the light of Natural Language Processing, this is more hard to address your problem (no simple NLP task matches with your problem definition) and you may not need any fancy model (complex) to resolve your problem.
You can start by simple document matching and computing a similarity score. If you have large collection of positive examples (well formatted and specified reports), you can construct a dictionary based on tf-idf weights. Then you can check the presence of the dictionary tokens. You can also think of this problem as a binary classification problem. There are good machine learning classifiers such as svm, logistic regression which works good for text data. You can use python and scikit-learn to build programs quickly and they are pretty easy to use. For text pre-processing, you can use NLTK.
Since the reports will be generated by field workers and there are few questions that will be answered by the reports (you mentioned about 3 specific components), i guess simple keyword matching techniques will be a good start for your research. You can gradually move to different directions based on your observations.
This seems like a perfect scenario to apply some machine learning to your process.
First of all, the data annotation problem is covered. This is usually the most annoying problem. Thankfully, you can rely on the curators. The curators can mark the specific sentences that specify: audience, relevance, purpose.
Train some models to identify these types of clauses. If all the classifiers fire for a certain document, it means that the document is properly formatted.
If errors are encountered, make sure to retrain the models with the specific examples.
If you don't provide yourself hints about the format of the document this is an open problem.
What you can do thought, is ask people writing report to conform to some format for the document like having 3 parts each of which have a pre-defined title like so
1. Purpose
Explains the purpose of the document in several paragraph.
2. Topic / Problem
This address the foobar problem also known as lorem ipsum feeling text.
3. Take away
What can the reader do after reading it?
You parse this document from .doc format for instance and extract the three parts. Then you can go through spell checking, grammar and text complexity algorithm. And finally you can extract for instance Named Entities (cf. Named Entity Recognition) and low TF-IDF words.
I've been trying to do something very similar with clinical trials, where most of the data is again written in natural language.
If you do not care about past data, and have control over what the field officers write, maybe you can have them provide these 3 extra fields in their reports, and you would be done.
Otherwise; CoreNLP and OpenNLP, the libraries that I'm most familiar with, have some tools that can help you with part of the task. For example; if your Regex pattern matches a word that starts with the prefix "inten", the actual word could be "intention", "intended", "intent", "intentionally" etc., and you wouldn't necessarily know if the word is a verb, a noun, an adjective or an adverb. POS taggers and the parsers in these libraries would be able to tell you the type (POS) of the word and maybe you only care about the verbs that start with "inten", or more strictly, the verbs spoken by the 3rd person singular.
CoreNLP has another tool called OpenIE, which attempts to extract relations in a sentence. For example, given the following sentence
Born in a small town, she took the midnight train going anywhere
CoreNLP can extract the triple
she, took, midnight train
Combined with the POS tagger for example; you would also know that "she" is a personal pronoun and "took" is a past tense verb.
These libraries can accomplish many other tasks such as tokenization, sentence splitting, and named entity recognition and it would be up to you to combine all of these tools with your domain knowledge and creativity to come up with a solution that works for your case.
What are the recommended methods for extracting locations from free text?
What I can think of is to use regex rules like "words ... in location". But are there better approaches than this?
Also I can think of having a lookup hash table table with names for countries and cities and then compare every extracted token from the text to that of the hash table.
Does anybody know of better approaches?
Edit: I'm trying to extract locations from tweets text. So the issue of high number of tweets might also affect my choice for a method.
All rule-based approaches will fail (if your text is really "free"). That includes regex, context-free grammars, any kind of lookup... Believe me, I've been there before :-)
This problem is called Named Entity Recognition. Location is one of the 3 most studied classes (with Person and Organization). Stanford NLP has an open source Java implementation that is extremely powerful: http://nlp.stanford.edu/software/CRF-NER.shtml
You can easily find implementations in other programming languages.
Put all of your valid locations into a sorted list. If you are planning on comparing case-insensitive, make sure the case of your list already is normalized.
Then all you have to do is loop over individual "words" in your input text and at the start of each new word, start a new binary search in your location list. As soon as you find a no-match, you can skip the entire word and proceed with the next.
Possible problem: multi-word locations such as "New York", "3rd Street", "People's Republic of China". Perhaps all it takes, though, is to save the position of the first new word, if you find your bsearch leads you to a (possible!) multi-word result. Then, if the full comparison fails -- possibly several words later -- all you have to do is revert to this 'next' word, in relation to the previous one where you started.
As to what a "word" is: while you are preparing your location list, make a list of all characters that may appear inside locations. Only phrases that contain characters from this list can be considered a valid 'word'.
How fast are the tweets coming in? As in is it the full twitter fire hose or some filtering queries?
A bit more sophisticated approach, that is similar to what you described is using an NLP tool that is integrated to a gazetteer.
Very few NLP tools will keep up to twitter rates, and very few do very well with twitter because of all of the leet speak. The NLP can be tuned for precision or recall depending on your needs, to limit down performing lockups in the gazetteer.
I recommend looking at Rosoka(also Rosoka Cloud through Amazon AWS) and GeoGravy